elwell67

Any suggestions on how to implement the stochastic predictor with a _different_ dropout rate than that which was used in training? I have tried to modify the layer attributes (.rate),...

The new version of theano has removed/renamed the max_pool_2d, resulting in an error in Layers.py To resolve, change "from theano.tensor.signal import downsample" to "from theano.tensor.signal import pool" Then, replace all...

Simple typo in Line 177 of io.general.nitf_elements.tres.unclass.CMETAA.py "PATH" should be "PATCH" in the middle line. ``` self.add_field('CG_PATCH_LTCORLL', 's', 11, value) self.add_field('CG_PATH_LNGCOLL', 's', 12, value) self.add_field('CG_PATCH_LAT_CONFIDENCE', 's', 9, value) ``` Thanks!

CMETAA AF_TYPE

2

Line 354 of io.complex.other_nitf.py Looks like cmetaa.AF_TYPE is expected to be stored as a list, but now it is stored as separate attributes (TYPE1, TYPE2, & TYPE 3) Suggest modifying...